{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T22:43:34Z","timestamp":1751496214030,"version":"3.37.3"},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2019,2,9]],"date-time":"2019-02-09T00:00:00Z","timestamp":1549670400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["SCHR 999\/5-2"],"award-info":[{"award-number":["SCHR 999\/5-2"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Lang Resources & Evaluation"],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1007\/s10579-018-09441-5","type":"journal-article","created":{"date-parts":[[2019,2,9]],"date-time":"2019-02-09T11:52:34Z","timestamp":1549713154000},"page":"677-706","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Token-based spelling variant detection in Middle Low German texts"],"prefix":"10.1007","volume":"53","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7941-2398","authenticated-orcid":false,"given":"Fabian","family":"Barteld","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chris","family":"Biemann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heike","family":"Zinsmeister","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,2,9]]},"reference":[{"key":"9441_CR1","unstructured":"Adesam, Y., & Bouma, G. (2016). Old Swedish part-of-speech tagging between variation and external knowledge. In Proceedings of the 10th SIGHUM workshop on language technology for cultural heritage, social sciences, and humanities, (pp. 32\u201342). Berlin, Germany: Association for Computational Linguistics."},{"key":"9441_CR2","unstructured":"Barteld, F. (2017). Detecting spelling variants in non-standard texts. In Proceedings of the student research workshop at the 15th conference of the European chapter of the association for computational linguistics, (pp. 11\u201322). Valencia, Spain: Association for Computational Linguistics."},{"key":"9441_CR3","unstructured":"Barteld, F., Schr\u00f6der, I., & Zinsmeister, H. (2015). Unsupervised regularization of historical texts for POS tagging. In Proceedings of the workshop on corpus-based research in the humanities (CRH), (pp. 3\u201312). Warsaw, Poland."},{"key":"9441_CR4","unstructured":"Barteld, F., Schr\u00f6der, I., & Zinsmeister, H. (2016). Dealing with word-internal modification and spelling variation in data-driven lemmatization. In Proceedings of the 10th SIGHUM workshop on language technology for cultural heritage, social sciences, and humanities, (pp. 52\u201362). Berlin, Germany: Association for Computational Linguistics."},{"key":"9441_CR5","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1162\/tacl_a_00051","volume":"5","author":"P Bojanowski","year":"2017","unstructured":"Bojanowski, P., Grave, E., Joulin, A., & Mikolov, T. (2017). Enriching word vectors with subword information. Transactions of the Association for Computational Linguistics, 5, 135\u2013146.","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"9441_CR6","unstructured":"Bollmann, M. (2012). (Semi-)automatic normalization of historical texts using distance measures and the Norma tool. In Mambrini F, Passarotti M, Sporleder C (eds) Proceedings of the second workshop on annotation of corpora for research in the humanities (ACRH-2), (pp. 3\u201314). Lisbon, Portugal."},{"key":"9441_CR7","unstructured":"Bollmann, M. (2013). POS tagging for historical texts with sparse training data. In Proceedings of the 7th linguistic annotation workshop and interoperability with discourse, (pp. 11\u201318). Sofia, Bulgaria: Association for Computational Linguistics."},{"key":"9441_CR8","unstructured":"Bollmann, M., & S\u00f8gaard, A. (2016). Improving historical spelling normalization with bi-directional LSTMs and multi-task learning. In Proceedings of COLING 2016, the 26th international conference on computational linguistics: technical papers, (pp. 131\u2013139). Osaka, Japan."},{"key":"#cr-split#-9441_CR9.1","unstructured":"Bollmann, M., Petran, F., & Dipper, S. (2011). Applying rule-based normalization to different types of historical texts-An evaluation. In Proceedings of the 5th language & technology conference: human"},{"key":"#cr-split#-9441_CR9.2","unstructured":"language technologies as a challenge for computer science and linguistics (LTC 2011), (pp. 339-344). Poznan, Poland."},{"key":"9441_CR10","doi-asserted-by":"crossref","unstructured":"Bollmann, M., Bingel, J., & S\u00f8gaard, A. (2017). Learning attention for historical text normalization by learning to pronounce. In Proceedings of the 55th annual meeting of the association for computational linguistics (volume 1: long papers), (pp. 332\u2013344). Vancouver, Canada : Association for Computational Linguistics","DOI":"10.18653\/v1\/P17-1031"},{"key":"9441_CR11","unstructured":"Chakrabarty, A., Pandit, O.A., & Garain, U. (2017). Context sensitive lemmatization using two successive bidirectional gated recurrent networks. In Proceedings of the 55th annual meeting of the association for computational linguistics (volume 1: long papers), (pp. 1481\u20131491). Vancouver, Canada: Association for Computational Linguistics."},{"key":"9441_CR12","unstructured":"Chollet F, et\u00a0al. (2015). Keras. https:\/\/github.com\/fchollet\/keras"},{"key":"9441_CR13","unstructured":"Chrupa\u0142a, G. (2014). Normalizing tweets with edit scripts and recurrent neural embeddings. In Proceedings of the 52nd annual meeting of the association for computational linguistics (volume 2: short papers), (pp. 680\u2013686). Baltimore, Maryland, USA: Association for Computational Linguistics."},{"key":"9441_CR14","unstructured":"Ciobanu, M.A., & Dinu, L.P. (2014). Automatic detection of cognates using orthographic alignment. In Proceedings of the 52nd annual meeting of the association for computational linguistics (volume 2: short papers), (pp. 99\u2013105). Baltimore, Maryland, USA: Association for Computational Linguistics."},{"key":"9441_CR15","unstructured":"Costa\u00a0Bertaglia, T.F., & Volpe\u00a0Nunes, MdG. (2016). Exploring word embeddings for unsupervised textual user-generated content normalization. In Proceedings of the 2nd workshop on noisy user-generated text (WNUT), (pp. 112\u2013120). Osaka, Japan: The COLING 2016 Organizing Committee."},{"issue":"3","key":"9441_CR16","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1145\/363958.363994","volume":"7","author":"FJ Damerau","year":"1964","unstructured":"Damerau, F. J. (1964). A technique for computer detection and correction of spelling errors. Communications of the ACM, 7(3), 171\u2013176.","journal-title":"Communications of the ACM"},{"key":"9441_CR17","unstructured":"Derczynski, L., Ritter, A., Clark, S., & Bontcheva, K. (2013). Twitter part-of-speech tagging for all: Overcoming sparse and noisy data. In Proceedings of the international conference recent advances in natural language processing (RANLP 2013), (pp. 198\u2013206). Hissar, Bulgaria."},{"key":"9441_CR18","unstructured":"Dipper, S., L\u00fcdeling, A., & Reznicek, M. (2013). NoSta-D: A corpus of German Non-Standard Varieties. In M. Zampieri, S. Diwersy (eds) Non-standard data sources in corpus-based research, ZSM-Studien, vol\u00a05, Shaker, (pp. 69\u201376)."},{"key":"9441_CR19","unstructured":"Ernst-Gerlach, A., & Fuhr, N. (2006). Generating search term variants for text collections with historic spellings. In M. Lalmas, A. MacFarlane, S. R\u00fcger, A. Tombros, T. Tsikrika & A. Yavlinsky (Eds.), Advances in Information Retrieval. ECIR 2006. Lecture Notes in Computer Science (Vol 3936, pp. 49\u201360). Berlin: Springer."},{"issue":"4","key":"9441_CR20","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1109\/TSMCC.2011.2161285","volume":"42","author":"M Galar","year":"2012","unstructured":"Galar, M., Fernandez, A., Barrenechea, E., Bustince, H., & Herrera, F. (2012). A review on ensembles for the class imbalance problem: Bagging-, boosting-, and hybrid-based approaches. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 42(4), 463\u2013484.","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews)"},{"key":"9441_CR21","unstructured":"Gomes, L., & Pereira Lopes, J.G. (2011). Measuring spelling similarity for cognate identification. In L. Antunes, H. S. Pinto (Eds.), Progress in artificial intelligence: 15th Portuguese conference on artificial intelligence. EPIA 2011. Lecture Notes in Computer Science (Vol 7026, pp. 624\u2013633). Berlin: Springer."},{"key":"9441_CR23","unstructured":"Hamilton, W.L., Leskovec, J., & Jurafsky, D. (2016). Diachronic word embeddings reveal statistical laws of semantic change. In Proceedings of the 54th annual meeting of the association for computational linguistics (volume 1: long papers), (pp. 1489\u20131501). Berlin, Germany: Association for Computational Linguistics."},{"issue":"1","key":"9441_CR24","doi-asserted-by":"publisher","first-page":"5:1","DOI":"10.1145\/2414425.2414430","volume":"4","author":"B Han","year":"2013","unstructured":"Han, B., Cook, P., & Baldwin, T. (2013). Lexical normalization for social media text. ACM Transactions on Intelligent Systems and Technology, 4(1), 5:1\u20135:27.","journal-title":"ACM Transactions on Intelligent Systems and Technology"},{"key":"9441_CR25","unstructured":"Hauser, A.W., & Schulz, K.U. (2007). Unsupervised learning of edit distance weights for retrieving historical spelling variations. In Proceedings of the first workshop on finite-state techniques and approximate search, (pp. 1\u20136). Borovets, Bulgaria."},{"issue":"1\u20132","key":"9441_CR26","first-page":"22","volume":"14","author":"A Hogenboom","year":"2015","unstructured":"Hogenboom, A., Bal, D., Frasincar, F., Bal, M., De Jong, F., & Kaymak, U. (2015). Exploiting emoticons in polarity classification of text. Journal of Web Engineering, 14(1\u20132), 22\u201340.","journal-title":"Journal of Web Engineering"},{"key":"9441_CR27","unstructured":"Jurish, B. (2010a). Comparing canonicalizations of historical German text. In Proceedings of the 11th Meeting of the ACL Special Interest Group on Computational Morphology and Phonology, (pp. 72\u201377). Uppsala, Sweden: Association for Computational Linguistics."},{"issue":"1","key":"9441_CR28","doi-asserted-by":"crossref","first-page":"23","DOI":"10.21248\/jlcl.25.2010.127","volume":"25","author":"B Jurish","year":"2010","unstructured":"Jurish, B. (2010b). More than words: Using token context to improve canonicalization of historical German. Journal for Language Technology and Computational Linguistics (JLCL), 25(1), 23\u201339.","journal-title":"Journal for Language Technology and Computational Linguistics (JLCL)"},{"key":"9441_CR29","unstructured":"Jurish, B. (2011). Finite-state canonicalization techniques for historical German. Ph.D. thesis, University of Potsdam, Germany."},{"key":"9441_CR30","unstructured":"Jurish, B., Thomas, C., & Wiegand, F. (2014). Querying the Deutsches Textarchiv. In U. Kruschwitz , F. Hopfgartner & C. Gurrin (eds) MindTheGap2014 (pp. 25\u201330). Berlin, Germany."},{"issue":"3","key":"9441_CR31","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1093\/llc\/fqq011","volume":"25","author":"M Kestemont","year":"2010","unstructured":"Kestemont, M., Daelemans, W., & Pauw, G. D. (2010). Weigh your words\u2013memory-based lemmatization for Middle Dutch. Literary and Linguistic Computing, 25(3), 287\u2013301.","journal-title":"Literary and Linguistic Computing"},{"key":"9441_CR32","unstructured":"Kim, Y. (2014). Convolutional neural networks for sentence classification. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), (pp. 1746\u20131751). Doha, Qatar: Association for Computational Linguistics."},{"key":"9441_CR33","unstructured":"Kingma, D.P., & Ba, J. (2014). Adam: A method for stochastic optimization. CoRR abs\/1412.6980."},{"key":"9441_CR34","unstructured":"Kobus, C., Yvon, F., & Damnati, G. (2008). Normalizing SMS: Are two metaphors better than one? In Proceedings of the 22nd international conference on computational linguistics (Coling 2008), (pp. 441\u2013448). Manchester, United Kingdom."},{"issue":"1","key":"9441_CR35","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1075\/ijcl.22.1.05kol","volume":"22","author":"M Koleva","year":"2017","unstructured":"Koleva, M., Farasyn, M., Desmet, B., Breitbarth, A., & Hoste, V. (2017). An automatic part-of-speech tagger for Middle Low German. International Journal of Corpus Linguistics, 22(1), 107\u2013140.","journal-title":"International Journal of Corpus Linguistics"},{"issue":"17","key":"9441_CR36","first-page":"1","volume":"18","author":"G Lemaitre","year":"2017","unstructured":"Lemaitre, G., Nogueira, F., & Aridas, C. K. (2017). Imbalanced-learn: A Python toolbox to tackle the curse of imbalanced datasets in machine learning. Journal of Machine Learning Research, 18(17), 1\u20135.","journal-title":"Journal of Machine Learning Research"},{"issue":"8","key":"9441_CR37","first-page":"707","volume":"10","author":"V Levenshtein","year":"1966","unstructured":"Levenshtein, V. (1966). Binary codes capable of correcting deletions, insertions, and reversals. Soviet Physics Doklady, 10(8), 707\u2013710.","journal-title":"Soviet Physics Doklady"},{"key":"9441_CR38","unstructured":"Li X. L., Liu B. (2005). Learning from positive and unlabeled examples with different data distributions. In J. Gama, R. Camacho, P. B. Brazdil, A. M. Jorge & L. Torgo (Eds.), Machine Learning: ECML 2005. Lecture Notes in Computer Science (Vol 3720, pp. 218\u2013229). Berlin: Springer."},{"key":"9441_CR39","unstructured":"Ljube\u0161i\u0107, N., Zupan, K., Fi\u0161er, D., & Erjavec, T. (2016). Normalising Slovene data: historical texts vs. user-generated content. In Proceedings of the 13th Conference on Natural Language Processing (KONVENS 2016), (pp. 146\u2013155). Bochum, Germany."},{"key":"9441_CR40","unstructured":"Loga\u010dev, P., Goldschmidt, K., & Demske, U. (2014). POS-tagging historical corpora: The case of Early New High German. In Proceedings of the thirteenth international workshop on treebanks and linguistic theories (TLT-13), (pp. 103\u2013112). T\u00fcbingen, Germany."},{"issue":"4","key":"9441_CR41","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1162\/0891201042544938","volume":"30","author":"S Mihov","year":"2004","unstructured":"Mihov, S., & Schulz, K. U. (2004). Fast approximate search in large dictionaries. Computational Linguistics, 30(4), 451\u2013477.","journal-title":"Computational Linguistics"},{"key":"9441_CR42","unstructured":"Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. CoRR abs\/1301.3781."},{"key":"9441_CR43","unstructured":"Mordelet, F., & Vert, J.P. (2014). A bagging SVM to learn from positive and unlabeled examples. Pattern Recognition Letters 37(Supplement C):201\u2013209."},{"key":"9441_CR44","unstructured":"Niebaum, H. (2000). Phonetik und Phonologie, Graphetik und Graphemik des Mittelniederdeutschen. In Sprachgeschichte: Ein Handbuch zur Geschichte der deutschen Sprache und ihrer Erforschung, 2nd edn (pp. 1422\u20131430). Berlin, Boston: DeGruyter."},{"key":"9441_CR45","unstructured":"Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, \u00c9. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research 12(Oct):2825\u20132830."},{"key":"9441_CR46","unstructured":"Pettersson, E., Megyesi, B., & Nivre, J. (2012). Rule-based normalisation of historical text \u2014 A diachronic study. In Proceedings of KONVENS 2012 (LThist 2012 workshop), (pp. 333\u2013341). Vienna, Austria."},{"key":"9441_CR47","unstructured":"Pettersson, E., Megyesi, B., & Nivre, J. (2013a). Normalisation of historical text using context-sensitive weighted levenshtein distance and compound splitting. In Proceedings of the 19th Nordic conference of computational linguistics (NODALIDA 2013), (pp. 163\u2013179). Oslo, Norway."},{"key":"9441_CR48","unstructured":"Pettersson, E., Megyesi, B., & Tiedemann, J. (2013). An SMT approach to automatic annotation of historical text. Proceedings of the Workshop on Computational Historical Linguistics at NODALIDA, 2013, (pp. 54\u201369). Oslo, Norway."},{"issue":"2","key":"9441_CR49","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1093\/llc\/fql020","volume":"21","author":"T Pilz","year":"2006","unstructured":"Pilz, T., Luther, W., Fuhr, N., & Ammon, U. (2006). Rule-based search in text databases with nonstandard orthography. Literary and Linguistic Computing, 21(2), 179\u2013186.","journal-title":"Literary and Linguistic Computing"},{"key":"9441_CR50","doi-asserted-by":"crossref","unstructured":"Piotrowski, M. (2012). Natural language processing for historical texts. Synthesis lectures on human language technologies 17, Morgan & Claypool Publishers.","DOI":"10.2200\/S00436ED1V01Y201207HLT017"},{"key":"9441_CR51","unstructured":"Schulz, K., & Mihov, S. (2001). Fast string correction with Levenshtein-automata. CIS-Report 01-127. Tech. rep., CIS, University of Munich."},{"key":"9441_CR52","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1007\/s10032-002-0082-8","volume":"5","author":"K Schulz","year":"2002","unstructured":"Schulz, K., & Mihov, S. (2002). Fast string correction with Levenshtein-automata. International Journal on Document Analysis and Recognition, 5, 67\u201385.","journal-title":"International Journal on Document Analysis and Recognition"},{"key":"9441_CR53","first-page":"53","volume":"7","author":"E Tjong Kim Sang","year":"2017","unstructured":"Tjong Kim Sang, E., Bollmann, M., Boschker, R., Casacuberta, F., Dietz, F., Dipper, S., et al. (2017). The CLIN27 shared task: Translating historical text to contemporary language for improving automatic linguistic annotation. Computational Linguistics in the Netherlands Journal, 7, 53\u201364.","journal-title":"Computational Linguistics in the Netherlands Journal"},{"key":"9441_CR22","unstructured":"van\u00a0der Goot, R., Plank, B., & Nissim, M. (2017). To normalize, or not to normalize: The impact of normalization on part-of-speech tagging. In Proceedings of the 3rd workshop on noisy user-generated text, (pp. 31\u201339). Copenhagen, Denmark: Association for Computational Linguistics."},{"key":"9441_CR54","unstructured":"Weissweiler L. & Fraser A. (2018). Developing a Stemmer for German Based on a Comparative Analysis of Publicly Available Stemmers. In G. Rehm, T. Declerck (Eds.), Language Technologies for the Challenges of the Digital Age. GSCL 2017. Lecture Notes in Computer Science (Vol 10713, pp. 81\u201394). Cham: Springer."},{"key":"9441_CR55","doi-asserted-by":"crossref","unstructured":"Yang, Y., & Eisenstein, J. (2016). Part-of-speech tagging for historical English. In Proceedings of the 2016 conference of the North American chapter of the association for computational linguistics: human language technologies (NAACL-HLT 2016), (pp. 1318\u20131328). San Diego, California, USA: Association for Computational Linguistics","DOI":"10.18653\/v1\/N16-1157"},{"issue":"6","key":"9441_CR56","doi-asserted-by":"publisher","first-page":"1091","DOI":"10.1109\/TPAMI.2007.1078","volume":"29","author":"L Yujian","year":"2007","unstructured":"Yujian, L., & Bo, L. (2007). A normalized Levenshtein distance metric. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(6), 1091\u20131095.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"}],"container-title":["Language Resources and Evaluation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10579-018-09441-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-018-09441-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-018-09441-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T14:19:02Z","timestamp":1694614742000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10579-018-09441-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2,9]]},"references-count":57,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["9441"],"URL":"https:\/\/doi.org\/10.1007\/s10579-018-09441-5","relation":{},"ISSN":["1574-020X","1574-0218"],"issn-type":[{"type":"print","value":"1574-020X"},{"type":"electronic","value":"1574-0218"}],"subject":[],"published":{"date-parts":[[2019,2,9]]},"assertion":[{"value":"9 February 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}